| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Robotic Manipulation | RoboCasa | Average Success Rate80.6 | 68 | |
| Robotic Tabletop Manipulation | RoboCasa GR1 Tabletop Tasks | Average Success Rate58.3 | 28 | |
| Robotic Manipulation | RoboCasa GR1 Tabletop | Average Success Rate72.8 | 24 | |
| Robotic Manipulation | RoboCasa Kitchen | Success Rate70.6 | 22 | |
| Robot Manipulation | RoboCasa GR1 | Average Success Rate63.2 | 20 | |
| CoffeeServeMug | RoboCasa | Success Rate49.1 | 20 | |
| Robotic Manipulation | RoboCasa365 | Average Success Rate42 | 18 | |
| Robotic Manipulation | RoboCasa Panda GR00T (test) | Success Rate67.2 | 16 | |
| Robot Manipulation | RoboCasa-GR1 24 tasks | Average Success Rate79.2 | 16 | |
| Tabletop Robot Manipulation | Robocasa Tabletop GR1 | Container Interaction Success Rate55.6 | 15 | |
| Closed-loop Planning | RoboCasa Rc-Pl | Success Rate34.4 | 14 | |
| Closed-loop Planning | RoboCasa Rc-R | Success Rate49 | 14 | |
| CoffeeSetupMug | RoboCasa | Success Rate20 | 13 | |
| Robot Manipulation | RoboCasa CloseDrawer | Success Rate82.3 | 12 | |
| Robotic Manipulation | RoboCasa GR1 Tabletop Manipulation (test) | PnP Bottle To Cabinet Close76 | 12 | |
| Kitchen manipulation | RoboCasa 24 kitchen manipulation tasks | Average Success Rate67.1 | 12 | |
| Robot Manipulation | RoboCasa365 pretraining (test) | Average Success Rate46.6 | 11 | |
| Robotic Manipulation | RoboCasa (val) | Average Success Rate64 | 10 | |
| Long-horizon household tasks | RoboCasa 24-task benchmark Human-50 few-shot | Pick & Place Success Rate40 | 9 | |
| Counter-to-Cabinet manipulation | RoboCasa365 Counter-to-Cabinet (ID Failure Episodes) | Success Rate22.8 | 8 | |
| Early Failure Detection | RoboCasa L (Seen) | ROC-AUC (q=0.25)82.7 | 8 | |
| Early Failure Detection | RoboCasa S (Unseen) | ROC-AUC (q=0.25)73.8 | 8 | |
| Early Failure Detection | RoboCasa S (Seen) | ROC-AUC (q=0.25)74.9 | 8 | |
| Early Failure Detection | RoboCasa (Unseen) | ROC-AUC (q=0.25)76.3 | 8 | |
| Early Failure Detection | RoboCasa (Seen) | ROC-AUC (q=0.25)77.4 | 8 |